TUTORIAL IN BIOSTATISTICS BAYESIAN DATA MONITORING IN CLINICAL-TRIALS

Many clinical trials organizations use regular interim analyses to mon itor the accruing results in large clinical trials. In disease areas s uch as cancer, where survival is usually a major outcome variable, eth ical considerations may lead to a stipulated requirement for data moni toring of mortality. This monitoring has frequently taken the form of limiting interim analyses to be few in number, and specifying an extre me p-value of, for example, p < 0.001 or p < 0.01 as grounds for early termination of the trial. Group-sequential methods are also used. How ever, none of these approaches formally assesses the impact that the r esults of a clinical trial may have upon clinical practice. Thus a tri al might be terminated early because of apparent treatment benefits, b ut might fail to influence sceptical clinicians to modify their future treatment policy. We discuss the application of Bayesian methods, inc luding the use of uninformative, sceptical and enthusiastic priors, an d demonstrate that the necessary calculations are both straightforward to perform and easy to interpret statistically and clinically. Method s are illustrated with interim analyses of a clinical trial in oesopha geal cancer. (C) 1997 by John Wiley & Sons, Ltd.